Physics background, biomedical mission.
I'm a postdoctoral researcher at the University of Bologna, where I develop computational methods to predict antimicrobial resistance, discover patient phenotypes, and make sense of high-dimensional omics data. My work spans MALDI-TOF mass spectrometry, multi-omics integration, and metagenomics, always with a focus on interpretability and clinical impact. Part of the Physics4MedicineLab group and the Multi-Omics and Health-Care Data Analytics Unit at Sant'Orsola Hospital.
PhD in Health and Technologies (University of Bologna, 2026), supervisor Prof. Gastone Castellani.
MaldiSuite - a Python ecosystem for MALDI-TOF spectral processing and analysis in antimicrobial resistance research. Visit the MaldiSuite website.
Three sklearn-compatible packages that chain into an end-to-end clinical AMR pipeline: preprocess with MaldiAMRKit, harmonise across batches/sites with MaldiBatchKit, classify with MaldiDeepKit.
| Research focus | Description |
|---|---|
|
AMR & clinical machine learning MALDI-TOF · supervised & generative learning · cross-site harmonisation |
Machine learning on mass spectra and clinical data to anticipate antimicrobial resistance ahead of culture-based diagnostics, with cross-site harmonisation and generative modelling extending the pipeline beyond single-instrument settings. → MaldiSuite, ResPredAI |
|
Infectious risk & pathogen surveillance patient phenotyping · survival & multi-state models · metagenomic surveillance |
Stratification of infectious risk in fragile populations such as transplant recipients, and surveillance of circulating pathogens through metagenomic monitoring and computational phenotyping. → phenocluster, CAMISIM-BrokenStick |
|
Computational genomics structural variants · somatic calling · long-read sequencing |
Discovery and interpretation of structural and somatic variants from short- and long-read sequencing, in clinically relevant genomic contexts. → APOBECSeeker, CATS |
|
Computational methodologies bioinformatic tools · open-source software · reproducible pipelines |
Open-source tools and reusable methods built around specific biomedical questions, designed to be reproducible and well-documented. → combatlearn, nestkit, MaldiBatchKit |
| Project | Description |
|---|---|
| combatlearn | Scikit-learn compatible ComBat batch-effect correction |
| ResPredAI | AI model to predict resistances in Gram-negative bloodstream infections |
| phenocluster | Unsupervised clinical phenotype discovery with survival and multistate modeling |
| CATS | Automated Cas9 nuclease comparison with ClinVar integration |
| CAMISIM-BrokenStick | Broken stick model extension for metagenomic simulation |
| APOBECSeeker | APOBEC-style mutation identification from multiple sequence alignment |
| nestkit | Nested cross-validation with calibration, threshold optimization, and statistical tests |
A curated list with BibTeX lives on my website; for the complete record, see my Google Scholar profile.
-
Rocchi, E. et al. Combining mass spectrometry and machine learning models for predicting Klebsiella pneumoniae antimicrobial resistance: a multicenter experience from clinical isolates in Italy. BMC Microbiology (2026).
-
Bonazzetti, C., Rocchi, E. et al. Artificial Intelligence model to predict resistances in Gram-negative bloodstream infections. npj Digital Medicine 8, 319 (2025).
-
Rocchi, E. et al. CATS: a bioinformatic tool for automated Cas9 nucleases activity comparison in clinically relevant contexts. Frontiers in Genome Editing 7, 1571023 (2025).